“Show the prompt change beside the result change.”
A score with no link to the edit that caused it cannot be acted on. The person sees the two prompt versions and the two sets of answers on one screen, and a regression points at a line. Dashboards that report quality on their own leave the person to guess which change did it.
The Context Matrix
Where this principle has been tested. Untested cells are honest gaps, not passing grades — seen evidence for one? Tell us.
| Chat | IDE | CLI | Canvas / Doc | Ambient / Background | |
|---|---|---|---|---|---|
| Coding | |||||
| Knowledge Work | ◐ | ||||
| Consumer | |||||
| Enterprise Ops | |||||
| Creative |
● supports · ◐ boundary · ✕ violates · blank untested
Linked Patterns
Boundary Conditions
- knowledge-work × canvas-doc × supervised
The Console shows versions side by side but names no baseline; the person ranks by reading.
Evidence
Braintrust aligns rows to a named baseline and shows the delta per row.
Langfuse shows score, cost and latency as changes against a baseline run.
The Console shows versions side by side but names no baseline; the person ranks by reading.
The Agents & Humans Briefing
Agentic experience design, coding agents, MCP, and the signals that matter — weekly, free, in about five minutes.
Free. No spam. Unsubscribe anytime.